Learning data visualization

library(tidyverse)

Loading tidyverse: ggplot2
Loading tidyverse: tibble
Loading tidyverse: tidyr
Loading tidyverse: readr
Loading tidyverse: purrr
Loading tidyverse: dplyr
Conflicts with tidy packages ---------------------------------
filter(): dplyr, stats
lag():    dplyr, stats

Relationship between engine size and fuel efficiency:

data = mpg
ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy))

ggplot(data) + geom_point(mapping = aes(x = hwy, y = cyl))

ggplot(data) + geom_point(mapping = aes(x = class, y = drv))

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy, color = class))

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy, size = class))

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy, alpha = class))

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy, shape = class))

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy), color = "blue")

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy, color = displ < 5))

Facets

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_wrap(~ class, nrow = 3)

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_grid(drv ~ cyl)

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_wrap(~ cyl)

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_grid(. ~ displ)

ggplot(data = mpg) + geom_point(mapping = aes(x = drv, y = cyl))

Geoms

ggplot(data) + geom_smooth(mapping = aes(x = displ, y = hwy, linetype = drv))

ggplot(data) + geom_smooth(mapping = aes(x = displ, y = hwy, linetype = drv, color = drv), method = loess) + geom_point(mapping = aes(x = displ, y = hwy, color = drv))

ggplot(data) + geom_smooth(mapping = aes(x = displ, y = hwy, color = drv), show.legend = F, method = loess)

ggplot(data) + geom_point(mapping = aes(x = displ, y = hwy)) + geom_smooth(mapping = aes( x = displ, y = hwy))

Bolji način za izvesti ovo gore - nema duplikacije koda!

ggplot(data, mapping = aes(x = displ, y = hwy)) + geom_point() + geom_smooth(method = loess)

ggplot(data, mapping = aes(x = displ, y = hwy)) + geom_point(mapping = aes(color = class)) + geom_smooth(data = filter(data, class == "suv"), color = "red")

ggplot(data, mapping = aes(x = displ, y = hwy, color = drv)) + geom_point() + geom_smooth(se = F)

ggplot(data, mapping = aes(x = displ, y = hwy)) + geom_point() + geom_smooth(se = F, method = loess) 

ggplot(data, mapping = aes(x = displ, y = hwy, group = drv)) + geom_point() + geom_smooth(se = F, method = loess)

ggplot(data, mapping = aes(x = displ, y = hwy, color = drv)) + geom_point() + geom_smooth(se = F, method = loess)

ggplot(data, mapping = aes(x = displ, y = hwy)) + geom_point(mapping = aes(color = drv)) + geom_smooth(se = F, method = loess)

ggplot(data, mapping = aes(x = displ, y = hwy)) + geom_point(mapping = aes(color = drv)) + geom_smooth(mapping = aes(linetype = drv), se = F, method = loess)

Statistical transformations

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = cut))

ggplot(data = diamonds) + stat_count(mapping = aes(x = cut))

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, y = ..prop.., group = 1))

ggplot(data = diamonds) + stat_summary(mapping = aes(x = cut, y = depth),
                                       fun.ymin = min,
                                       fun.ymax = max,
                                       fun.y = median)

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, y = ..prop..))

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = color, y = ..prop..))

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = clarity))

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = clarity, position = "identity", alpha = 1/5))

Ignoring unknown aesthetics: position

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = clarity), position = "fill")

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")

Jittering - adding random noise to make graphs more revealing at large scales

ggplot(data = mpg) + geom_jitter(mapping = aes(x = displ, y = hwy))

ggplot(data = mpg, mapping = aes(x = cty, y = hwy)) + geom_jitter(mapping = aes(color = "red")) + geom_count(mapping = aes(alpha = 4/5))

Box plots

ggplot(data = mpg, mapping = aes(x = factor(cyl), y = hwy)) + geom_boxplot()

Coordinate systems

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + geom_boxplot()

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + geom_boxplot() + coord_flip()

bar <- ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = cut), show.legend = F, width = 1) + theme(aspect.ratio = 1) + labs(x = NULL, y = NULL)

bar

bar + coord_flip()

bar + coord_polar()